new·Plugin 0.5.0: agents verify and hand offTwo new MCP tools, live for every connected agent right now. brain_verify checks a claim against a brain before you act on it — supported / contradicted / not_covered, with the evidence notes; anything unconfirmed is flagged to the brain's owner as a gap. brain_handoff is the baton between sessions and agents: stop mid-task, leave where you got to, and the next session — this agent tomorrow or a different tool entirely — takes it and continues. brain_list now shows open handoffs, and /mind grows a relay feed.all news →
mozg.betaSign in

explore / AI & agents / mozg / Vercel AI SDK

AI SDK · Core

Answer questions about the AI SDK core APIs exactly as specified: generateText, streamText, generateObject, tools and tool calling, agents, UI hooks — each function's options, types and defaults.

3,303 notes · updated 2026-08-05 · trained 80%

since last sitting: +2 newly passed — this brain is learning · the verified changelog →

use this brain
# sign in to get a token
$ claude mcp add --transport http mozg \
https://mozg.sh/mcp --header "Authorization: Bearer …"
> use mozg/ai-sdk-core — …
Sign in — get this command with your token in it

New here? Sign in and this exact command appears with your token already inside — copy, paste into your terminal, done.

Or just add it

Sign in and add it, and every agent you have connected can read it — nothing to download, and it stays current as the author updates it.

Sign in to add it

Ask it things like

answers 26/30 on its latest exam · anti-bluff 2/6
How does streamText differ from generateText in terms of return value structure?Core API Options & Defaults✓
What is the exact structure of a tool object, including all required properties?Tools & Tool Calling✓
What are the required configuration parameters for useChat and what do they specify?UI Hooks - useChat✓
What parameter replaces maxSteps in the AI SDK v5, and what type does it accept?Agents✓
What parameters does generateText accept for controlling output generation?Core API Options & Defaults✓
How should you modify a Zod schema to be compatible with OpenAI structured outputs?generateObject & Structured Output✓
What causes NoObjectGeneratedError when using OpenAI structured outputs, and how do you fix it?generateObject & Structured Output✓
What is the difference between server-side and client-side tool execution in the AI SDK?Tools & Tool Calling✓

What it can answer

30 checks
80%
✓UI Hooks - useChat8 / 8
✓Tools & Tool Calling7 / 7
▲Core API Options & Defaults4 / 5
▲Agents3 / 4
▲generateObject & Structured Output3 / 4
▲UI Hooks - useCompletion & Stream Protocol1 / 2
exam badge — share this score →

Inside

  • Node streaming text with chat history example · ai sdk core apis
  • streamText function signature and parameters · ai sdk core apis
  • streamText returns result object with textStream property · ai sdk core apis
  • maxOutputTokens default value or common usage in streamText · core api options & defaults
  • Example: streamText with manual reader control · ai sdk core apis
  • streamText function parameters for Node · ai sdk core apis
  • Use getReader() method to manually control stream reading · ai sdk core apis
  • Iterate over textStream with for-await loop · ai sdk core apis
  • streamText stream property for custom formatting · ai sdk core apis
  • StreamTextResult.stream event types · ai sdk core apis
  • Custom stream format example with tool calls · tools & tool calling
  • Client-side Server-Sent Events parsing pattern · ai sdk core apis
  • stopWhen parameter with isStepCount condition · agents
  • Server-Sent Events format for custom stream · ai sdk core apis

Licence

CC BY-NC-SA 4.0

Use it, copy it, build on it, with credit. Selling it is not allowed.